docs: replace em/en dashes with hyphens

README.md

@@ -15,23 +15,23 @@ pipeline_tag: object-detection
 library_name: gguf
 ---
 
-# locate-anything.cpp — GGUF
+# locate-anything.cpp - GGUF
 
 GGUF builds of [`nvidia/LocateAnything-3B`](https://huggingface.co/nvidia/LocateAnything-3B)
-for **[locate-anything.cpp](https://github.com/mudler/locate-anything.cpp)** — a C++/ggml
+for **[locate-anything.cpp](https://github.com/mudler/locate-anything.cpp)** - a C++/ggml
 inference engine for open-vocabulary detection / visual grounding, no Python at inference time.
 
 **Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team.**
 
 The detections are the same as the official PyTorch implementation (the engine is
-parity-gated against it), and it runs faster — on CPU and GPU.
+parity-gated against it), and it runs faster - on CPU and GPU.
 
 ## Files
 
 | File | Bits (LM) | Size | Notes |
 | ---- | --------- | ---- | ----- |
 | `locate-anything-f16.gguf`  | f16  | ~9.2 GB | LM matmuls in f16, everything else f32 |
-| `locate-anything-q8_0.gguf` | q8_0 | ~6.3 GB | near-lossless; **box-identical** to f32 — recommended |
+| `locate-anything-q8_0.gguf` | q8_0 | ~6.3 GB | near-lossless; **box-identical** to f32 - recommended |
 | `locate-anything-q6_k.gguf` | q6_k | ~5.5 GB | box-identical to f32 |
 | `locate-anything-q5_k.gguf` | q5_k | ~5.1 GB | sub-pixel box drift |
 | `locate-anything-q4_k.gguf` | q4_k | ~4.7 GB | smallest; sub-pixel box drift |
@@ -65,7 +65,7 @@ through q6_k:
 
 Run against the official model exactly as its model card documents (bf16), greedily, on one
 GB10 GPU. Precision-matched (our **f16** vs its bf16) ours is **~1.7×** faster; the
-recommended **q8_0** build (box-identical) is **~1.9–2.1×**:
+recommended **q8_0** build (box-identical) is **~1.9-2.1×**:
 
 ![GB10 GPU speedup vs official bf16](gpu_speedup.png)
 
@@ -73,7 +73,7 @@ recommended **q8_0** build (box-identical) is **~1.9–2.1×**:
 
 Only the Qwen2 language-model matmuls (`attn_{q,k,v,o}`, `ffn_{gate,up,down}`, `lm.output`)
 are quantized. The MoonViT vision tower, the projector, all norms and biases, and the two
-host-read f32 tensors (`lm.tok_embd`, `vit.pos_emb`) stay **f32** — so the parity-sensitive
+host-read f32 tensors (`lm.tok_embd`, `vit.pos_emb`) stay **f32** - so the parity-sensitive
 vision path is untouched. q8_0/q6_k are box-identical; lower bit-widths trade a little box
 precision for size.